Patrick Lefler·Jul 16The Case for Kernel Density Estimation Instead of a Parametric Loss DistributionA five-year loss history rarely contains enough tail events to say what the tail looks like. That scarcity is the whole argument for…
Farshad Noravesh·Nov 21, 2025Score function of the forward DistributionLet’s go step by step and connect kernel density estimation (KDE) with learning the score function at some time t in a diffusion or SDE…
Muskan Marghani·Nov 2, 2025Unpacking Data Distributions: A Friendly Introduction to Kernel Density Estimation (KDE)Ever looked at a dataset and wondered, “What’s really going on here? How are these numbers spread out?” We often start with histograms, and…
Himanshu Pandey·Oct 1, 2025Density estimation and their typesDensity estimation is a non—parametric estimation technique. Let me quickly explain what non-parametric estimation is.
Mohith·Aug 22, 2025Moving Past Histograms: Smoothing Out Distributions with KDEThe role of kernels and bandwidth in smoothing data
Zhe Sun, Phd·Jul 30, 2025Difference between Outlier Detection and Novelty Detectionclean/dirty Assumption
Rayan Yassminh·Jul 11, 2025Math for ML: Kernels Explained Simply with ExamplesDiscover the power of kernel methods in machine learning , from SVMs to Kernel PCA, KDE, and Image kernels.A response icon2A response icon2
Avinash·Jun 21, 2025Density-Based Outlier AnalysisDensity-Based Outlier Analysis is a powerful framework for identifying outliers by analyzing how densely packed data points are in a…
Zhe Sun, Phd·May 26, 2025Kernel Density Estimation for anomaly detectionIn a previous article, I explored three broad categories of anomaly detection methods: Rule-Based, Value-Based, and Sequence-Based. Among…A response icon1A response icon1
